Left: "Initial image" VS Right: result "imagined".
I will also explain step by step how you can try yourself! Your head will blow up 🤯
1. Super Mario.
More 🧵👇
2. Guybrush Threepwood.
3. Wizzard.
4. Cute girls.
5. Sonic with ugly hands 😂 (is a work in progress for AIs).
6. Charmander (from "love you I'm cute" to "I will finish you").
7. Fez map (several versions).
8. Link.
9. Peach (well... more or less, hahaha).
10. Donkey Kong.
11. Eastward.
I was surprised by how beautiful the whale has turned out.
Disclaimer! with this experiment I'm not saying that the new images are better. In fact, #pixelart drives me crazy and many of the original images transmit a lot more to me.
I'm just exploring the potential of this tech. Something like this has so many potential applications.
12. Tales of Phantasia.
Even more difficult: not only pixelated, but also blurry. The mask is a cool addition 🤣
13. Thimbleweed Park.
14. Day of the Tentacle.
15. This is interesting: pixelated avatar of my friend.
Here we can see how the AI, having been trained with 5000M images, generates a bit of what it wants (the information is invented).
Of course: none of them look like him in real life 🤣
And well, the AI has done a little what it wanted, as always, hahaha. I forgot to describe that the bottom thing was a bear. I only put "dinosaurs". And of course, this is what happened.
4/ Then, use a prompt like this: "[a detailed description of what you want], highly detailed, smooth, sharp focus, 8k, ray tracing, digital painting, concept art illustration, by artgerm, trending on artstation, nikon d850".
5/ Important! You will have to play with "Image Strength". The sweet point is around 25%-35%
6/ Important! You will have to play with "Cfg Scale" too. The trick is to use a high value around 16-20.
7/ Be patient! Lot of times you will have to cherry pick a good result after lot of trying. Usually they are bit... monstrous.
8/ By the using the "seed number" (for the Mario example I used 4128836123 and StableDiffusion 1.5) you can iterate over a promising image by "anchoring" it with the seed.
Hey, @EMostaque thanks a lot for SD! It is REALLY useful. I also tried with your avatar 😊
Hope u liked this thread!
Would you like to learn more about AI image generation?
🔥 Follow me! 🔥
I'm working on a prompts bundle I will release soon, with detailed explanations to be able to create awesome images! It will include the MOST ADVANCED prompts I found.
If you liked this thread, a RT to the first tweet of the thread will encourage me to keep posting, thanks! 🙏👇
Lot of people are playing with Generative AI but only a few like Ben Nash have mastered it.
Here's how... Oops! What a CLICKBAIT thread starter I just wrote, LOL. But seriously, this is a totally legit step-by-step tutorial:
1/ Step one: go follow @bennash. Man, thank you for letting me share this tutorial!
By the way, if someone is reading this and is interested in creating tutorials for Magnific, and you would like me to share your work, just let me know! ❤️
2/ Generate the base image using Midjourney. Prompt in ALT.
I remember spending 30 hours on texturing, lighting, and rendering to finish a render like this. And now, anyone can do it in seconds. Everything is going to change!
Here's a step-by-step tutorial 🧵👇
1/ First, the transformation, using the brand new Magnific Style Transfer:
I used a reference image with the style I wanted to transfer to the base render and increased Structure Strength up to 100%.
Together with the reference image, it's a good idea to provide a prompt to guide the auto AI texturing:
"Loft interior design, photography, beautiful, bricks and wooden floor, three artistic paintings on the wall, dezeen magazine, photography"
Transform any image, controlling the amount of style transferred and the structural integrity ✨ Infinite use cases! 3d, video games, interior design, for fun...
Details, 10 tutorials & HUGE surprise 🧵👇
If you can't wait, here's the link to that website that most of you already love (and we love you back! ❤️).
It seems that @juliewdesign_ has perfectly cracked the parameters for perfect Portraits with Magnific!
Here's a TUTORIAL that emerged from a chat with her. She has allowed me to share her secret mojo with you 😉👇
Midjourney prompt: "young blonde woman in blue shirt with big, in the style of soft and rounded forms, avacadopunk, webcam photography, , dark teal and light gray, dutch marine scenes, detailed facial features --ar 57:71 --v 6.0"
Magnific parameters:
So, the first thing that may surprise you is that we haven't used any of the two Portraits presets.
Sometimes, it seems that a good prompt in Magnific and using the 'Standard' preset can yield better results.